Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8763
    Prev
    Next
    INDEX
    Explanations

    words related to criminal activities, specifically focusing on robbery

    oai_token-act-pair · gpt-3.5-turbo

    references to robbery and related criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Active
    -0.80
     Spectrum
    -0.79
     Syn
    -0.73
    isters
    -0.70
     tuned
    -0.67
     Integ
    -0.66
    Opt
    -0.66
     voc
    -0.66
    Active
    -0.66
     Zucker
    -0.64
    POSITIVE LOGITS
     robbery
    3.67
     robberies
    2.95
     robbers
    2.53
     robber
    2.34
     burglary
    2.25
     robbing
    2.07
     robbed
    1.96
     theft
    1.93
     thefts
    1.74
     burgl
    1.64
    Activations Density 0.026%

    No Known Activations